River

7.9K posts

River

River

@RiverNotFlowing

Beigetreten Aralık 2015
972 Folgt85 Follower
River retweetet
Philipp Spiess
Philipp Spiess@PhilippSpiess·
@badlogicgames You can self-host github.com/agentlogs/agen… It supports codex, claude code, pi, opencode, and cline already (including automatic uploads via olugjns) and has a basic secret-scanner too. Maybe this could announce public transcripts somewhere so you can still own them?
English
3
4
54
6.7K
River
River@RiverNotFlowing·
@schrockn Muting any idiot that parrots "mcp is dead" Yes mcp may die but not so you give agents a full shell to fuck around in your system doing god know what and spending multiple round trips for what could have been an atomic tool call whose permission explicitly controlled by the user
English
0
0
0
13
Nick Schrock
Nick Schrock@schrockn·
The mcp v cli debate getting tiresome. Clis are better for devs working in local coding agents. MCPs better for enterprise use cases integrating with things like slack and web chat uis. Neither is probably where we end up in a few years.
Karan Vaidya@KaranVaidya6

Okay, @gdb is team CLI all the way. @garrytan thinks MCPs suck. So we hit the streets of SF to see if the city agreed. We posed a simple question: MCP or CLI? - Basically everyone under the age of 35 said CLI - One person said MCP was as bloated as Java - & unsurprisingly, numerous people told us to touch grass Final score- MCP: 3 vs CLI: 17 SF has spoken, and @composio listened. Our universal CLI is now live! Drop your best CLI vs MCP hot take in the comments and we'll send the best ones some very sick gear 👀 Link to try our CLI in the next thread ⬇️

English
3
0
16
3.2K
River retweetet
Hari
Hari@HarivanshRathi·
All agentcomputer.ai machines now ship with deskctl.dev Your coding agent already has a bash tool. Deskctl gives it a way to output bash scripts with wait blocks and grouped actions to be able to automate long computer-use tasks in a single agent loop.
English
10
11
101
9.1K
River retweetet
bitcelium e/cli 🦞🍄
Thank you champ! Lifesaver 🛟. Would've been happy if my Claude would've been as helpful as his buddies, I guess it still has to learn from you 🫶🏽. I specifically asked it yesterday because I got a bit tired of having this as an unsolved problem for my android work and it needed steering 🥲, only saw the light after I saw it.
bitcelium e/cli 🦞🍄 tweet mediabitcelium e/cli 🦞🍄 tweet media
English
0
1
1
94
River retweetet
Rork
Rork@rork·
Introducing Rork Max Publishing Rork Max can now fill your entire App Store page without you ever touching it. It fills in all the fields, generates beautiful icons & screenshots, makes a mock review so you don't get rejected, and submits for you. Yes, iPad screenshots too.
English
143
101
1.7K
603.7K
River retweetet
No Cats No Life
No Cats No Life@NoCatsNoLife_m·
Are they birds?
English
89
7.9K
46.1K
465.3K
River
River@RiverNotFlowing·
@crawfax @zippytonto @volcaholic1 All of east asia has some form of bidet. Not only we're cleaner and more efficient we're also simply more obsessed with cleanliness that's why. Even before washing machine in Chinese culture you don't wash underwear together with proper clothing.
English
2
0
1
67
Volcaholic 🌋
Volcaholic 🌋@volcaholic1·
In China, washing machines are evolving fast. Triple-drum machines can run three separate loads at once. One main drum plus two smaller ones for delicates, all with separate water systems. Some models use AI and can be controlled from your phone.
English
261
511
5K
905.4K
River
River@RiverNotFlowing·
@volcaholic1 funny that we have more competition and innovation in suposed state monopoly
English
0
0
0
283
River retweetet
Tech Daily 24/7
Tech Daily 24/7@techdaily24·
The `mesh-llm` project facilitates large-scale LLM inference by pooling distributed, spare GPU capacity. It establishes a mesh network architecture to optimize resource utilization for demanding AI workloads.
Tech Daily 24/7 tweet media
English
1
1
1
19
Thomas Ricouard
Thomas Ricouard@Dimillian·
The worst feature of macOS is defaulting to reopening all windows after a reboot or an update. Why would I want to do that????
English
74
2
231
34.4K
River
River@RiverNotFlowing·
@FractalVeritas @advaitpaliwal 2 possible eplanations: - they made suboptimal choice - they made optimal choice, you just don't get the condition under which the choice was made
English
0
0
0
60
Dovraîxs
Dovraîxs@FractalVeritas·
@advaitpaliwal whyyyy do people keep using javascript for this kind of stuff..
English
3
0
10
7.9K
Advait Paliwal
Advait Paliwal@advaitpaliwal·
I built Feynman, Claude Code for research. I gave it a question and it came back 30 minutes later with a cited meta analysis. It can also replicate experiments on Runpod, audit claims against code, and simulate peer review. Open source & MIT license, link below
English
134
437
4.9K
314.2K
River
River@RiverNotFlowing·
@Shreyaskapale @garrytan Why would it not? People have been doing all sort of crazy things with agents.md being the only thing standardised
English
3
0
0
38
Shreyas Kapale
Shreyas Kapale@Shreyaskapale·
@RiverNotFlowing @garrytan how would define model, turns, spending caps, other configs - multiple people using different frameworks and formats? how will md file accommodate all that?
English
1
0
0
24